Welcome to the LLM for Coding repository, where we harness the power of large language models (LLMs) to enhance coding experiences. This repository contains Jupyter notebooks that interface with state-of-the-art code generation models.
code_llama.ipynb
: Utilizes the CodeLlama-13B-Instruct-fp16 model for generating code with a focus on following instructions closely.code_with_gemma.ipynb
: Leverages the codegemma-2b model, optimized for generating high-quality code snippets.code_llama-3.ipynb
: Employs the llama-3 model, designed for versatile code generation across various programming languages.
To use these notebooks:
- Ensure you have Jupyter installed. If not, install it using:
pip install jupyter
- Clone this repository:
git clone [email protected]:imanoop7//llm_for_coding.git
- Navigate to the cloned directory and start Jupyter: cd llm_for_coding 4.Open the desired notebook and follow the instructions within to start coding with the power of LLMs. Prerequisites Python 3.8+ Jupyter Notebook Internet connection (for model access) Models Here’s a brief overview of the models used in our notebooks:
- CodeLlama-13B-Instruct-fp16: A 13-billion parameter model fine-tuned for following specific coding instructions.
- codegemma-2b: A 2-billion parameter model that excels in generating concise and accurate code.
- llama-3: A versatile model capable of understanding and generating code in multiple programming languages. ##Contributing Contributions are what make the open-source community such an amazing place to learn, inspire, and create. Any contributions you make are greatly appreciated.
If you have a suggestion that would make this better, please fork the repo and create a pull request. You can also simply open an issue with the tag “enhancement”.
Don’t forget to give the project a star! Thanks again!
Distributed under the MIT License. See LICENSE for more information.